{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TGG24TRQL6WWQHAH2ZYNOOFN7S","short_pith_number":"pith:TGG24TRQ","schema_version":"1.0","canonical_sha256":"998dae4e305fad681c07d670d738adfc92c1b6ca37c64c9f48efe1fd80376fdc","source":{"kind":"arxiv","id":"2412.12173","version":1},"attestation_state":"computed","paper":{"title":"A NotSo Simple Way to Beat Simple Bench","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Angus McLean, Soham Sane","submitted_at":"2024-12-12T16:04:31Z","abstract_excerpt":"This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs) by leveraging iterative reasoning and feedback-driven methodologies. Building on the limitations identified in the SimpleBench benchmark, a dataset designed to evaluate logical coherence and real-world reasoning, we propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness. Through comparative analysis of state-of-the-art models, including Claude 3 Opus, Claude 3.5, GPT- 4o, and o1-preview, we demonstrate that iterative reasoni"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.12173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T16:04:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3612261b681adaf2559d3a6597a3a34da8646c2be36f4cf1b04dd9cc26a405e2","abstract_canon_sha256":"89f79ba3fda4e951ec3b1e0b088b9ce333047071b8169f99d4b63d70d88a07f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:11.018723Z","signature_b64":"Lw3gZy043n57EHuhGwmB50LZ9d64M8k7hhsyMrGCdTAocU0Tx6olf3Nwrx5UdQG+i1pXCxIqG2vr1jFB9muyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"998dae4e305fad681c07d670d738adfc92c1b6ca37c64c9f48efe1fd80376fdc","last_reissued_at":"2026-07-05T09:50:11.018301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:11.018301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A NotSo Simple Way to Beat Simple Bench","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Angus McLean, Soham Sane","submitted_at":"2024-12-12T16:04:31Z","abstract_excerpt":"This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs) by leveraging iterative reasoning and feedback-driven methodologies. Building on the limitations identified in the SimpleBench benchmark, a dataset designed to evaluate logical coherence and real-world reasoning, we propose a multi-step prompting strategy coupled with global consistency checks to improve model accuracy and robustness. Through comparative analysis of state-of-the-art models, including Claude 3 Opus, Claude 3.5, GPT- 4o, and o1-preview, we demonstrate that iterative reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12173","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.12173/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.12173","created_at":"2026-07-05T09:50:11.018361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12173v1","created_at":"2026-07-05T09:50:11.018361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12173","created_at":"2026-07-05T09:50:11.018361+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGG24TRQL6WW","created_at":"2026-07-05T09:50:11.018361+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGG24TRQL6WWQHAH","created_at":"2026-07-05T09:50:11.018361+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGG24TRQ","created_at":"2026-07-05T09:50:11.018361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02289","citing_title":"Evalita-LLM: Benchmarking Large Language Models on Italian","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S","json":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S.json","graph_json":"https://pith.science/api/pith-number/TGG24TRQL6WWQHAH2ZYNOOFN7S/graph.json","events_json":"https://pith.science/api/pith-number/TGG24TRQL6WWQHAH2ZYNOOFN7S/events.json","paper":"https://pith.science/paper/TGG24TRQ"},"agent_actions":{"view_html":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S","download_json":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S.json","view_paper":"https://pith.science/paper/TGG24TRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12173&json=true","fetch_graph":"https://pith.science/api/pith-number/TGG24TRQL6WWQHAH2ZYNOOFN7S/graph.json","fetch_events":"https://pith.science/api/pith-number/TGG24TRQL6WWQHAH2ZYNOOFN7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S/action/storage_attestation","attest_author":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S/action/author_attestation","sign_citation":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S/action/citation_signature","submit_replication":"https://pith.science/pith/TGG24TRQL6WWQHAH2ZYNOOFN7S/action/replication_record"}},"created_at":"2026-07-05T09:50:11.018361+00:00","updated_at":"2026-07-05T09:50:11.018361+00:00"}